Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Encap offset calculation is incorrect in esp6, from Sabrina Dubroca.

 2) Better parameter validation in pfkey_dump(), from Mark Salyzyn.

 3) Fix several clang issues on powerpc in selftests, from Tanner Love.

 4) cmsghdr_from_user_compat_to_kern() uses the wrong length, from Al
    Viro.

 5) Out of bounds access in mlx5e driver, from Raed Salem.

 6) Fix transfer buffer memleak in lan78xx, from Johan Havold.

 7) RCU fixups in rhashtable, from Herbert Xu.

 8) Fix ipv6 nexthop refcnt leak, from Xiyu Yang.

 9) vxlan FDB dump must be done under RCU, from Ido Schimmel.

10) Fix use after free in mlxsw, from Ido Schimmel.

11) Fix map leak in HASH_OF_MAPS bpf code, from Andrii Nakryiko.

12) Fix bug in mac80211 Tx ack status reporting, from Vasanthakumar
    Thiagarajan.

13) Fix memory leaks in IPV6_ADDRFORM code, from Cong Wang.

14) Fix bpf program reference count leaks in mlx5 during
    mlx5e_alloc_rq(), from Xin Xiong.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (86 commits)
  vxlan: fix memleak of fdb
  rds: Prevent kernel-infoleak in rds_notify_queue_get()
  net/sched: The error lable position is corrected in ct_init_module
  net/mlx5e: fix bpf_prog reference count leaks in mlx5e_alloc_rq
  net/mlx5e: E-Switch, Specify flow_source for rule with no in_port
  net/mlx5e: E-Switch, Add misc bit when misc fields changed for mirroring
  net/mlx5e: CT: Support restore ipv6 tunnel
  net: gemini: Fix missing clk_disable_unprepare() in error path of gemini_ethernet_port_probe()
  ionic: unlock queue mutex in error path
  atm: fix atm_dev refcnt leaks in atmtcp_remove_persistent
  net: ethernet: mtk_eth_soc: fix MTU warnings
  net: nixge: fix potential memory leak in nixge_probe()
  devlink: ignore -EOPNOTSUPP errors on dumpit
  rxrpc: Fix race between recvmsg and sendmsg on immediate call failure
  MAINTAINERS: Replace Thor Thayer as Altera Triple Speed Ethernet maintainer
  selftests/bpf: fix netdevsim trap_flow_action_cookie read
  ipv6: fix memory leaks on IPV6_ADDRFORM path
  net/bpfilter: Initialize pos in __bpfilter_process_sockopt
  igb: reinit_locked() should be called with rtnl_lock
  e1000e: continue to init PHY even when failed to disable ULP
  ...

8 files changed, 121 insertions, 23 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index f7ee8fa377ad..6ccecbd39476 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -5,10 +5,60 @@
 
 #include "test_btf_map_in_map.skel.h"
 
+static int duration;
+
+static __u32 bpf_map_id(struct bpf_map *map)
+{
+	struct bpf_map_info info;
+	__u32 info_len = sizeof(info);
+	int err;
+
+	memset(&info, 0, info_len);
+	err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len);
+	if (err)
+		return 0;
+	return info.id;
+}
+
+/*
+ * Trigger synchronize_rcu() in kernel.
+ *
+ * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu()
+ * if looking up an existing non-NULL element or updating the map with a valid
+ * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map,
+ * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then
+ * cleanup. At the end, at least one synchronize_rcu() would be called.
+ */
+static int kern_sync_rcu(void)
+{
+	int inner_map_fd, outer_map_fd, err, zero = 0;
+
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno))
+		return -1;
+
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
+					     sizeof(int), inner_map_fd, 1, 0);
+	if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) {
+		close(inner_map_fd);
+		return -1;
+	}
+
+	err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0);
+	if (err)
+		err = -errno;
+	CHECK(err, "outer_map_update", "failed %d\n", err);
+	close(inner_map_fd);
+	close(outer_map_fd);
+	return err;
+}
+
 void test_btf_map_in_map(void)
 {
-	int duration = 0, err, key = 0, val;
-	struct test_btf_map_in_map* skel;
+	int err, key = 0, val, i;
+	struct test_btf_map_in_map *skel;
+	int outer_arr_fd, outer_hash_fd;
+	int fd, map1_fd, map2_fd, map1_id, map2_id;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -18,32 +68,78 @@ void test_btf_map_in_map(void)
 	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
 		goto cleanup;
 
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	outer_arr_fd = bpf_map__fd(skel->maps.outer_arr);
+	outer_hash_fd = bpf_map__fd(skel->maps.outer_hash);
+
 	/* inner1 = input, inner2 = input + 1 */
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0);
 	skel->bss->input = 1;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2);
 
 	/* inner1 = input + 1, inner2 = input */
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0);
+	bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0);
 	skel->bss->input = 3;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3);
 
+	for (i = 0; i < 5; i++) {
+		val = i % 2 ? map1_fd : map2_fd;
+		err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+		err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+	}
+
+	map1_id = bpf_map_id(skel->maps.inner_map1);
+	map2_id = bpf_map_id(skel->maps.inner_map2);
+	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
+	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
+
+	test_btf_map_in_map__destroy(skel);
+	skel = NULL;
+
+	/* we need to either wait for or force synchronize_rcu(), before
+	 * checking for "still exists" condition, otherwise map could still be
+	 * resolvable by ID, causing false positives.
+	 *
+	 * Older kernels (5.8 and earlier) freed map only after two
+	 * synchronize_rcu()s, so trigger two, to be entirely sure.
+	 */
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+
+	fd = bpf_map_get_fd_by_id(map1_id);
+	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+	fd = bpf_map_get_fd_by_id(map2_id);
+	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 8294ae3ffb3c..43c9cda199b8 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -318,6 +318,9 @@ class DebugfsDir:
                 continue
 
             if os.path.isfile(p):
+                # We need to init trap_flow_action_cookie before read it
+                if f == "trap_flow_action_cookie":
+                    cmd('echo deadbeef > %s/%s' % (path, f))
                 _, out = cmd('cat %s/%s' % (path, f))
                 dfs[f] = out.strip()
             elif os.path.isdir(p):
diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c
index 99f8f582c02b..c5e805980409 100644
--- a/tools/testing/selftests/bpf/verifier/event_output.c
+++ b/tools/testing/selftests/bpf/verifier/event_output.c
@@ -112,6 +112,7 @@
 	"perfevent for cgroup sockopt",
 	.insns =  { __PERF_EVENT_INSNS__ },
 	.prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT,
+	.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 	.fixup_map_event_output = { 4 },
 	.result = ACCEPT,
 	.retval = 1,
diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh
index eb8e2a23bbb4..43a948feed26 100755
--- a/tools/testing/selftests/net/forwarding/ethtool.sh
+++ b/tools/testing/selftests/net/forwarding/ethtool.sh
@@ -252,8 +252,6 @@ check_highest_speed_is_chosen()
 	fi
 
 	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
-	# Remove the first speed, h1 does not advertise this speed.
-	unset speeds_arr[0]
 
 	max_speed=${speeds_arr[0]}
 	for current in ${speeds_arr[@]}; do
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 8c8c7d79c38d..2c522f7a0aec 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off,
 	int fds[2], fds_udp[2][2], ret;
 
 	fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n",
-		typeflags, PORT_BASE, PORT_BASE + port_off);
+		typeflags, (uint16_t)PORT_BASE,
+		(uint16_t)(PORT_BASE + port_off));
 
 	fds[0] = sock_fanout_open(typeflags, 0);
 	fds[1] = sock_fanout_open(typeflags, 0);
diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 422e7761254d..bcb79ba1f214 100644
--- a/tools/testing/selftests/net/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
@@ -329,8 +329,7 @@ int main(int argc, char **argv)
 	bool all_tests = true;
 	int arg_index = 0;
 	int failures = 0;
-	int s, t;
-	char opt;
+	int s, t, opt;
 
 	while ((opt = getopt_long(argc, argv, "", long_options,
 				  &arg_index)) != -1) {
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index ceaad78e9667..3155fbbf644b 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
 	if (rbuf[0] != ts->data)
 		error(1, 0, "payload mismatch. expected %c", ts->data);
 
-	if (labs(tstop - texpect) > cfg_variance_us)
+	if (llabs(tstop - texpect) > cfg_variance_us)
 		error(1, 0, "exceeds variance (%d us)", cfg_variance_us);
 
 	return false;
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 4555f88252ba..a61b7b3da549 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -344,7 +344,7 @@ int main(int argc, char *argv[])
 {
 	struct sockaddr_storage listenaddr, addr;
 	unsigned int max_pacing_rate = 0;
-	size_t total = 0;
+	uint64_t total = 0;
 	char *host = NULL;
 	int fd, c, on = 1;
 	char *buffer;
@@ -473,12 +473,12 @@ int main(int argc, char *argv[])
 		zflg = 0;
 	}
 	while (total < FILE_SZ) {
-		ssize_t wr = FILE_SZ - total;
+		int64_t wr = FILE_SZ - total;
 
 		if (wr > chunk_size)
 			wr = chunk_size;
 		/* Note : we just want to fill the pipe with 0 bytes */
-		wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0);
+		wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0);
 		if (wr <= 0)
 			break;
 		total += wr;